CoChat

GooAQ: Open Question Answering with Diverse Answer Types

Open access
Khashabi, Daniel, Ng, Amos, Khot, Tushar, Sabharwal, Ashish, Hajishirzi, Hannaneh, Callison-Burch, Chris · 2021 · Findings of the Association for Computational Linguistics: EMNLP 2021
Cited by 31

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

Abstract

While day-to-day questions come with a variety of answer types, the current open questionanswering (QA) literature represents isolated efforts on niche response types, with a heavy focus on specific kinds of short responses (people, places, etc.).To address this gap, we present GOOAQ, a large-scale dataset collected from Google questions and answers, containing 3 million questions with diverse answer types ranging from factual short answers to snippets to collections.Our human evaluation shows that 94% of the mined answers are accurate, enabling fine-tuning a pre-trained language model for answering GOOAQ questions.We use this dataset to study inherent differences between models producing different answer types, and observe interesting trends.For example, in line with recent work, LM's strong performance on GOOAQ's shortanswer questions heavily benefits from annotated data.However, their surprisingly high quality in generating coherent and accurate answers for questions requiring long responses (such as 'how' and 'why' questions) is less reliant on observing annotated data and mainly supported by their pre-training.Moreover, we show that GOOAQ is a valuable training resource, resulting in strong performance on the recent ELI5 long-answers dataset.We release GOOAQ to facilitate further research on improving QA with diverse response types. 1Question: how many calories burned 30 minutes crossfit?Answer(short: from the snippet): 260 calories Answer(snippet): According to the American Council on Exercise, a 115-pound person running for 30 minutes at a slow-to-moderate pace (a 10-minute mile) would burn about 260 calories. Question: what are the steps for decision making? Answer(collection): [Step 1: Identify the decision You realize that you need to make a decision. , Step 2: Gather relevant information. Step 3: Identify the alternatives. Step 4: Weigh the evidence. Step 5: Choose among alternatives. Step 6: Take action. Step 7: Review your decision & its consequences.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2021.findings-emnlp.38

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 13 references

Cited by

See all 31

Metadata

Authors
Khashabi, D., Ng, A., Khot, T., Sabharwal, A., Hajishirzi, H., & Callison-Burch, C.
Venue
Findings of the Association for Computational Linguistics: EMNLP 2021
Published
2021
Pages
421-433
OpenAlex
W3154570112
Cited by
31
References
13
FWCI
3.08
Type
conference paper
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: GooAQ: Open Question Answering with Diverse Answer Types. https://app.cochat.ai/papers/10.18653/v1/2021.findings-emnlp.38
The paper
Khashabi, D., Ng, A., Khot, T., Sabharwal, A., Hajishirzi, H., & Callison-Burch, C. (2021). GooAQ: Open Question Answering with Diverse Answer Types. Findings of the Association for Computational Linguistics: EMNLP 2021. https://doi.org/10.18653/v1/2021.findings-emnlp.38

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.